The baseline model

read image

Image preprocessing

extract features from selected layers

compute loss

output

result output

Replace MaxPooling with AveragePooling

Change content layers

Custom weights for different style layers

Adjusting $\alpha:\beta$

Final Output

With content_layer = block4_2, lr = 5, iteration = 200, weights_per_style_layer = (0.15,10,0.2,10,0.2),